Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
60
40
515
martin
PRO
martintomov
Follow
Tonic's profile picture
pwndayma's profile picture
NikolayKozloff's profile picture
24 followers
·
9 following
AI & ML interests
None yet
Recent Activity
liked
a model
12 days ago
arnaudstiegler/sd-model-gameNgen-60ksteps
reacted
to
merve
's
post
with 🚀
16 days ago
Apollo is a new family of open-source video language models by Meta, where 3B model outperforms most 7B models and 7B outperforms most 30B models 🧶 ✨ the models come in 1.5B https://huggingface.co/Apollo-LMMs/Apollo-1_5B-t32, 3B https://huggingface.co/Apollo-LMMs/Apollo-3B-t32 and 7B https://huggingface.co/Apollo-LMMs/Apollo-7B-t32 with A2.0 license, based on Qwen1.5 & Qwen2 ✨ the authors also release a benchmark dataset https://huggingface.co/spaces/Apollo-LMMs/ApolloBench The paper has a lot of experiments (they trained 84 models!) about what makes the video LMs work ⏯️ Try the demo for best setup here https://huggingface.co/spaces/Apollo-LMMs/Apollo-3B they evaluate sampling strategies, scaling laws for models and datasets, video representation and more! > The authors find out that whatever design decision was applied to small models also scale properly when the model and dataset are scaled 📈 scaling dataset has diminishing returns for smaller models > They evaluate frame sampling strategies, and find that FPS sampling is better than uniform sampling, and they find 8-32 tokens per frame optimal > They also compare image encoders, they try a variation of models from shape optimized SigLIP to DINOv2 they find https://huggingface.co/google/siglip-so400m-patch14-384 to be most powerful 🔥 > they also compare freezing different parts of models, training all stages with some frozen parts give the best yield They eventually release three models, where Apollo-3B outperforms most 7B models and Apollo 7B outperforms 30B models 🔥
liked
a model
16 days ago
FastVideo/FastMochi
View all activity
Organizations
martintomov
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
liked
a model
12 days ago
arnaudstiegler/sd-model-gameNgen-60ksteps
Text-to-Image
•
Updated
19 days ago
•
352
•
1
liked
3 models
16 days ago
FastVideo/FastMochi
Updated
23 days ago
•
6
FastVideo/FastMochi-diffusers
Text-to-Video
•
Updated
17 days ago
•
166
•
13
FastVideo/FastHunyuan
Text-to-Video
•
Updated
2 days ago
•
495
•
132
liked
a Space
19 days ago
Running
on
Zero
356
👈🖼️👉
Flux Fill Outpainting
liked
a model
20 days ago
hkchengrex/MMAudio
Updated
9 days ago
•
38
liked
a dataset
24 days ago
pandaphd/camera_settings
Viewer
•
Updated
29 days ago
•
3.5k
•
201
•
7
liked
a model
25 days ago
JeffreyXiang/TRELLIS-image-large
Image-to-3D
•
Updated
27 days ago
•
520k
•
272
liked
a Space
25 days ago
Running
on
Zero
2.44k
🏢
TRELLIS
Scalable and Versatile 3D Generation from images
liked
a model
28 days ago
briaai/BRIA-2.3-ControlNet-Generative-Fill
Text-to-Image
•
Updated
1 day ago
•
76
•
24
liked
a Space
28 days ago
Running
on
Zero
672
🚀
Flux Style Shaping
Optical illusions and style transfer with FLUX
liked
3 models
about 1 month ago
Kijai/HunyuanVideo_comfy
Updated
16 days ago
•
195
tencent/HunyuanVideo
Text-to-Video
•
Updated
16 days ago
•
8.9k
•
1.34k
showlab/ShowUI-2B
Updated
29 days ago
•
13.1k
•
212
liked
a Space
about 1 month ago
Running
on
Zero
189
💻
ShowUI
liked
2 models
about 1 month ago
Comfy-Org/mochi_preview_repackaged
Updated
Nov 5, 2024
•
50
Qwen/QwQ-32B-Preview
Text Generation
•
Updated
Nov 29, 2024
•
109k
•
•
1.48k
liked
a Space
about 1 month ago
Running
on
Zero
431
📈
IC Light V2-Vary
liked
2 models
about 1 month ago
Yuanshi/OminiControl
Image-to-Image
•
Updated
24 days ago
•
8.48k
•
101
nvidia/Hymba-1.5B-Instruct
Text Generation
•
Updated
about 4 hours ago
•
11.1k
•
213
Load more